High Definition Map Solution
Abstract
Raw map data generated from various sensors might have gaps and other defects. Although map providers are currently working on generating highly accurate maps of public roads with a large coverage, gaps and other defects still exist in the map data and need to be identified. When it comes to autonomous vehicles, occurrences of such defects would impair the localization of the vehicle, and therefore the reliability of the autonomous driving system in the vehicle. Map features need to be validated for large discrepancies. If the differences are such that localization cannot be guaranteed, the autonomous driving system must be notified, thus returning control to the human driver. So, it is necessary to develop a methodology to fully evaluate raw map data and improve its quality (identity and fill gaps).
Challenge
An OEM sought to enhance its HD Map testing process by addressing challenges and limitations they had, including changes in real-world environments, missing information in map data, high redundancy, limited control on route selection, long time for executing tests in a simulation and lack of automation.
The Solution
- An intelligent route planner algorithm for test case generation
- Integration of map features and additional requirements for better coverage
- Identification of map variants to optimize test case design and selection
- Prioritization of test case execution to focus on critical areas
- Elimination of test case redundancy to improve efficiency
- Full automation of the testing process to increase efficiency
The Results
100%
map coverage and covered a slightly shorter length than the brute-force approach.
89%
reduction in the number of test cases and only one iteration of QAMapTest required.
100%
elimination of redundant distance.
99%
reduction of HD Map validation execution time.
The implementation of QAMapTest successfully resolved the OEM’s testing challenges and limitations. The solution eliminated test case redundancy, identified map variants for reusing test cases, reduced the number of test cases, and achieved 100% coverage over 100 times faster than the brute-force approach.